One of the biggest bottlenecks for the advancement of research in MIR is the lack of very large and openly available corpora of music data to train and test machine learning models. That meetup will discuss how this can be changed.
When: 17th July 2017, 7.30 pm
Where: CRCLR, Rollbergstraße 26, Berlin
Xavier Serra, who is Associate Professor of the Department of Information and Communication Technologies and Director of the Music Technology Group at the Universitat Pompeu Fabra in Barcelona, will talk about the initiatives his group is involved with to tackle this issue. He will present an overview of methods that look to extract information from symbolic representations such as digital scores, pattern recognition, harmonic sequence analysis, and melodic reduction.
Ryan Groves from Melodrive will talk about Computational Music Theory: Working with Symbolic Data. He received his B.S. in Computer Science from UCLA and continued on to complete a Master’s in Music Technology from McGill University. He is the former Director of R&D for Zyaa and developed a musical messenger app that automatically sings your texts, called Ditty.
Ryan also just recently wrote a very interesting blog post about Feminism as a male data scientist.